unilm
unilm copied to clipboard
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
output:“ O O O O O I-医院名称 I-医院名称 O I-医院名称 I-医院名称 I-医院名称 I-医院名称 I-医院名称 I-医院名称 O O O O O O O ” The dataset and input data are correct....
**Describe** Model I am using (MarkupLM) I have some questions about pre-training of MarkupLM. 1. there are many webpages with long text. how did you handle the long pages? 2....
**Describe** Model I am using LayoutLmv3: I downloaded base model, and use the config file based on Publaynet. I training the model on [Article Regions dataset](https://github.com/cxsoto/article-regions),a little object detection dataset...
ModuleNotFoundError during installation process of DiT. `shapely` reference should be in [requirements.txt](https://github.com/microsoft/unilm/blob/cd2eb8ade8b6e475aefa9b769ced2eefc4245a3e/dit/requirements.txt)
**Describe** Model I am using (UniLM, MiniLM, LayoutLM ...): **LayoutReader** Hi @zlwang-cs I am using `layoutreader` to predict layout-only data like this, which the order is from right to left,...
Hello, when I using Layoutreader for order prediction, it will predict some duplicated boxes. For example, the number of input boxes is 55, there are 22 boxes are duplicated, and...
Thanks for your excellent work! I am really looking forward to your open-source code to help me understand your work.When will the code and models of VLMo be released? Thanks~
We are getting very good accuracy on English documents for form understanding using LayoutLMv3 but now we have to extract information from French documents also, so please suggest me which...
I am training latest version of layoutLMv3 model but while starting training `trainer.train()` getting bellow error. Please help me to resolve it. I am using v100 4 GPUs: ``` RuntimeError...
Is it possible to use LayoutLMv3 for object detection using the Transformers library? I can see that LayoutLMv3SequenceClassification and LayoutLMv3TokenClassification exist? I am not sure how these would cover object...